Topic: The development of clinical AI cycle: from signal discovery to pragmatic trials and real-world deployment Speaker: Professor Chin Lin, Department of Medicine, National Defense Medical University Time: March 11, 2026 (Wednesday), 12:10 – 14:00 p.m. Venue: The Management Building, 11F, AI Lecture Hall or Livestreaming https://reurl.cc/GG72GG Registration: https://reurl.cc/R9AMeD or scan QR code on poster  About the Speaker:   Dr. Chin Lin is a data scientist whose work centers on establishing clinical evidence standards for medical artificial intelligence. His research integrates large-scale electronic health records, electrocardiography, medical imaging, and home-based sensing to develop AI systems that are not only accurate, but clinically actionable and outcome-improving. He has led or co-led more than ten pragmatic randomized controlled trials evaluating AI-enabled clinical workflows, with results published in Nature Medicine, NEJM AI, Radiology, and Nature Communications. His team developed an AI-ECG platform that has received TFDA approval and USFDA Breakthrough Device Designation, has been transferred to industry, and deployed across multiple hospitals and rural screening programs. A central theme of his work is treating AI not as a standalone model, but as a system-level intervention that links prediction, clinical action, and patient outcomes within real-world healthcare environments. Abstract: Recent advances in artificial intelligence (AI) have shifted medical AI research from model-centric performance reporting toward evidence-based clinical impact. In this talk, I introduce the concept of the clinical AI cycle, a comprehensive framework that describes how clinical AI can progress from signal discovery, through pragmatic clinical trials, to real-world deployment in healthcare systems. At the stage of signal discovery, I will illustrate how routinely collected data—such as electrocardiograms (ECGs), chest radiographs (CXRs), and electronic health records (EHRs)—can be leveraged using data-driven approaches and multimodal foundation models to identify latent disease risks. This paradigm enables a single examination to support opportunistic screening for multiple diseases, overcoming the traditional one-test-one-disease limitation. The second stage focuses on pragmatic trials, where AI models are evaluated not merely by predictive accuracy but by their ability to trigger pre-specified clinical actions and improve patient outcomes. By embedding AI alerts into real clinical workflows and evaluating them using randomized controlled and digital trial platforms, AI is positioned as an actionable decision engine rather than a passive prediction tool. Finally, in real-world deployment, I will demonstrate how clinical AI can be scaled to community screening, home healthcare, and wearable devices, and integrated with large-scale health databases. This deployment completes the clinical AI cycle, allowing continuous learning, post-deployment surveillance, and discovery of new clinical insights. Organizers: Institute of Health Data Science ※ Registration needed.

Topic: Merging Sensors, AI, and VR for Athlete Training Speaker: Prof. Min-Chun Hu — Associate Chair, Department of Computer Science at National Tsing Hua University. Time: March 10, 2026 (Tuesday), 2:00 – 4:00 p.m. Venue: The Management Building, 11F, AI Lecture Hall Join Online: https://reurl.cc/EbkDzv or scan QR code on poster  About the Speaker:   Dr. Min-Chun Hu received her Ph.D. from the Graduate Institute of Networking and Multimedia, National Taiwan University in 2011. After graduation, she worked as a postdoctoral researcher at the Research Center for Information Technology Innovation in Academia Sinica, and later served as an assistant/associate professor in the Department of Computer Science and Information Engineering at National Cheng Kung University. She is currently a professor in the Department of Computer Science at National Tsing Hua University. Dr. Hu has been recognized with numerous awards, including Exploration Research Award of Pan Wen Yuan Foundation (2015), Outstanding Young Researcher Award from the Computer Society of the Republic of China (2017), IEEE Tainan Section Best Young Professional Member Award (2018), Google Research exploreCSR Award (2021-2024), CES Innovation Awards (2023), and NSTC Ta-You Wu Memorial Award (2023). Her research interests encompass digital signal processing, multimedia content analysis, computer vision, computer graphics, virtual reality, and augmented reality. As a passionate basketball enthusiast, she has long been dedicated to developing sports technology that assists athletes in training and performance analysis. Dr. Hu previously served as Deputy Executive Director of the Taiwan Institute of Sports Science and is also the co-founder of NeuinX, a startup specializing in AI technology for sports analysis. Abstract: Tactical and skill training play a crucial role in athletic development. With the support of artificial intelligence (AI) technology, it is now possible to track the ball and players to detect fine-grained events, helping coaches collect detailed statistics and infer each team’s tactics. Additionally, virtual reality (VR) technology can be leveraged to enhance both the effectiveness and experience of tactical and skill-based training. This talk will introduce modern systems that utilize AI and VR to help athletes conveniently gather valuable sports data and improve a wide range of skills. Organizers: College of Intelligent Computing & Artificial Intelligence Research Center ※ No registration needed.

Topic: Integrating genetics, multimodal medical imaging, and AI for high-precision risk prediction of type 2 diabetes Speaker: Hsin-Chou Yang, Ph.D. Research Fellow and Director of the Institute of Statistical Science, Academia Sinica Time: December 24, 2025 (Wednesday), 12:10 – 14:00 p.m. Venue: The Management Building, 11F, AI Lecture Hall or Livestreaming https://reurl.cc/R9Ynp6 Registration: https://forms.office.com/r/YGHweb7HNT or scan QR code on poster  About the Speaker:   Dr. Hsin-Chou Yang is a statistician, bioinformatician, and data scientist at Academia Sinica, where he is a Full Research Fellow and Director. His work integrates methodological innovation with biomedical applications, including major studies on the Han Chinese cohort (Nature), AI-based diabetes prediction (Nature Communications), and COVID-19 viral subtypes (PNAS). He is an elected ISI and GYA member, recipient of multiple national awards, active journal editor/reviewer, conference chair, and mentor to young scientists. Abstract: In this talk, the speaker will share how the team combined genetics, medical imaging, and rich health data from over 131,000 Taiwan Biobank participants to better understand and predict Type 2 Diabetes (T2D). Using AI—from deep learning on raw images to polygenic and imaging risk scores—the study uncovered genetic links, causal relationships, and new insights into how the body signals T2D risk. The integrated model achieved an AUC of 0.944, demonstrating strong potential for scalable, real-world precision health. Organizers: Institute of Health Data Science ※ Registration needed.  

Topic: How to Know Earlier? Using Machine Learning to Identify the Risk of Disease Development - the Case of Glaucomatous Neuropathy Speaker: Dr. Cezary Mazurek , Poznan Supercomputing and Networking Center Time: December 16, 2025 (Tuesday), 11:00–12:00 p.m. Venue: The Management Building, 11F, AI Lecture Hall About the Speaker: Dr. Cezary Mazurek, Computer Scientist, his professional activity has been associated with the development of the Poznan Supercomputing and Networking Center (PCSS) since its establishment in 1993. He served as CEO of PCSS from 2019 to 2024 and at that time he successfully brought it onto the path of developing infrastructure and applications of quantum computing and AI, and is now continuing this thread with a focus on applications in Life Sciences and Personalized Medicine. For over 30 years, he has been involved in the development of Polish and European e-infrastructure for science and is currently one of the most experienced leaders in R&D projects, many of which he has successfully implemented in practice. To date, he has led development of more than 40 national and international R&D projects. His R&D work has focused on integrating various specialized software components into consistent systems for digital science with emphasis on software governance. In recent years, he has been involved in the development of domain research infrastructures, such as for digital humanities, as well as for personalized medicine.   Cezary’s scientific activities mainly focus on applying machine learning methods for early detection of disease development mechanisms. A solution led by him to support pre-symptomatic diagnosis of glaucoma development using machine learning received patent protection from the Japan Patent Office in 2023 and from European Patent Office in 2025. He is currently extending his interests to advanced methods of data collection and analysis in a digital twin model. He is author or co-author of over 100 papers in professional journals and conference proceedings. Since 2020 the President of Wielkopolska ICT Cluster. Since 2023 the member of GÉANT Association Board of Directors. In 2024 he initiated the establishment of a national consortium EBRAINS-PL and became the member of EBRAINS National Node Board. IEEE Senior Member, member of IEEE Computer Society as well as IEEE Computational Intelligence Society. Abstract: In recent years, there has been a significant increase in the number of studies on the role of artificial/assisted intelligence in the diagnosis of eye diseases. Scientific work in this field is mainly based on the analysis of imaging examinations. However, the development of diseases is very often caused by functional disorders that remain hidden for many years and are not immediately visible in the form of clinical symptoms. An example of such diseases is glaucomatous neuropathy. Since 2014, we have been working in a transdisciplinary team on intelligent decision support technology in the functional diagnosis and treatment of glaucomatous neuropathy. The functionality of the developed software platform is based on the assessment of non-intraocular-pressure risk factors in the development of glaucomatous neuropathy, enabling glaucoma specialists to be supported in the recognition, quantification, and differential diagnosis of glaucomatous neuropathy. The developed system, based on a predictive model, enables the identification of individuals with ocular hypertension at significantly high risk of conversion to primary open-angle glaucoma, as well as the assessment of the effectiveness of glaucoma therapy. The solution has been patented in Japan and Europe. The above example shall also help to present the latest trends in our research work on neurodegenerative diseases and brain health initiated around the EBRAINS research infrastructure, artificial intelligence, and quantum computing technology. Organizers: College of Intelligent Computing & Artificial Intelligence Research Center ※ No registration needed.

Curious what top engineers in the U.S. really do day to day? Want to hear authentic insights from a Google AI Platform engineer and a former Machine Learning Engineering Manager at Accenture? Don’t miss this event! Join Stephen and Rohisha as they share what life is truly like as engineers in the U.S., giving you a clearer picture of careers in AI/ML and data science—and inspiring your own path forward. Seats are limited, so sign up now! Time: December 4, 2025 (Thursday), 12:10 – 14:00 p.m. Venue: 14th Floor, CoIC Conference Room, Management Building Registration: https://forms.office.com/r/VBSgJpV4L8 or scan QR code on poster  About the Speaker:   Stephen Koo is a Staff Software Engineer at Google specializing in AI and backend systems. He leads the evaluation infrastructure for AI features on the Workspace AI Platform team and previously worked on the core serving stack for Generative AI in Workspace. Before that, he was on the Gmail & Chat team focusing on reliable email processing and smart features. He also developed deep learning models for speech recognition and helped rebuild Stanford AI’s CodaLab platform. He holds an M.S. and B.S. from Stanford.   Rohisha Adke was most recently a Machine Learning Engineering Manager at Accenture, leading teams that built data science and machine learning solutions for clients across energy, retail, healthcare, and tech. She began as a data scientist in Accenture’s global Data Science Center of Excellence, working with clients and tech partners to develop data and ML solutions. She also enjoyed co-presenting at conferences and mentoring aspiring technologists. Rohisha holds an M.S. in Statistics and a B.S. in Mathematical & Computational Science from Stanford and is currently on sabbatical. Abstract: Join us to hear from Stephen Koo, an AI engineer at Google, and Rohisha Adke, former Machine Learning Engineering Manager at Accenture. They will share their experiences, key skills, and challenges working as engineers in the U.S. tech industry across AI, data science, and machine learning fields. Organizers: CoIC ※ Registration needed.